Scraper Wikipédia

npm install firecrawl zod

import { Firecrawl } from 'firecrawl';
import { z } from 'zod';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const result = await firecrawl.scrape('https://en.wikipedia.org/wiki/JavaScript', {
    formats: [{
        type: 'json',
        schema: z.object({
            name: z.string(),
            creator: z.string(),
            firstAppeared: z.string(),
            typingDiscipline: z.string(),
            website: z.string()
        })
    }]
});

console.log(result.json);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const searchResult = await firecrawl.search('quantum computing site:en.wikipedia.org', {
    limit: 10,
    sources: [{ type: 'web' }], // { type: 'news' }, { type: 'images' }
    scrapeOptions: {
        formats: ['markdown']
    }
});

console.log(searchResult);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const result = await firecrawl.scrape('https://en.wikipedia.org/wiki/Artificial_intelligence', {
    formats: ['markdown'], // par ex. html, links, etc.
    onlyMainContent: true
});

console.log(result);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const mapResult = await firecrawl.map('https://en.wikipedia.org/wiki/Portal:Computer_science');

console.log(mapResult.links);
// Renvoie un tableau d'URL sans contenu

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const crawlResult = await firecrawl.crawl('https://en.wikipedia.org/wiki/Portal:Artificial_intelligence', {
    limit: 10,
    scrapeOptions: {
        formats: ['markdown']
    }
});

console.log(crawlResult.data);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

// Attendre la fin
const job = await firecrawl.batchScrape([
    'https://en.wikipedia.org/wiki/Machine_learning',
    'https://en.wikipedia.org/wiki/Artificial_intelligence',
    'https://en.wikipedia.org/wiki/Deep_learning'],
    {
        options: {
            formats: ['markdown']
        },
        pollInterval: 2,
        timeout: 120
    }
);


console.log(job.status, job.completed, job.total);

console.log(job);